Metraipolis › archive › dc_acca27414f2c
Certified AI Triage of ICU Alarms — arXiv:2609.12365
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12365
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:15:41.816Z
- SHA-256 of the archived text
e8a1dd05d60ef8bcf0dc510d98de90730fb7fe2144f8683bbefe4a8a4a106324- Stable URL of this page
https://metraipolis.com/documento/dc_acca27414f2c
How to cite
Certified AI Triage of ICU Alarms — arXiv:2609.12365 — arXiv (en), https://arxiv.org/abs/2609.12365 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acca27414f2c (Metraipolis archive dc_acca27414f2c, sha256 e8a1dd05d60ef8bcf0dc510d98de90730fb7fe2144f8683bbefe4a8a4a106324)
BibTeX
@misc{dcacca27414f2c,
title = {Certified AI Triage of ICU Alarms — arXiv:2609.12365},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12365},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acca27414f2c; sha256 e8a1dd05d60ef8bcf0dc510d98de90730fb7fe2144f8683bbefe4a8a4a106324},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12365. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In the VTaC benchmark 71% of ventricular-tachycardia alarms are false, but silencing a real one can delay recognition of a dangerous arrhythmia. We reframe alarm reduction as three-way triage (retain, suppress, or defer) and bound the decision this analysis treats as harmful: among suppressed alarms, the fraction that were genuine stays below a user-set budget with 95% confidence, under i.i.d. event sampling. Alarms sharing a waveform record are dependent, so the clustered analysis is a sensitivity check. On the official split a 5% budget certifies in all three seeds, suppressing 74.8% of false alarms while silencing 1.5% of genuine ones, at AUROC 0.953 and Challenge Score 83.33, numerically comparable to the strongest of the eleven published systems. Our central finding measures what multiplicity costs: the correction charges for every candidate, so a finer grid can certify strictly less. Under held-out calibration the 885-cell grid we declared certifies 1 of 15 fold-runs, while choosing the grid on a separate selection partition certifies 8. We project the calibration volume each budget needs, making an uncertifiable budget a design parameter. Finally, adding a learned reliability dimension to the policy grid did not sharpen the certified frontier. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.12365 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T03:05:44.040Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).